不同应用场景下的监控视频前景目标提取方法研究

Research on Foreground Target Extraction Method of Surveillance Video under Different Application Scenarios

目前,各类传感器广泛覆盖在人类生存的各个角落里,持续捕捉着地球表层的空间场景结构与变化过程,真实地记录着精细的场景信息和运动目标信息,为人们提供了丰富的视频信息。人们通常对视频监控中的前景目标(运动目标)较为感兴趣,而前景目标提取是运动目标跟踪和事件监测的前提,直接影响监测的精确性。本文针对监控视频的前景目标提取问题,提出了不同应用场景下的监控视频前景目标提取方法,并通过实验验证了方法的可行性。

At present, various types of sensors are widely covered in all corners of human existence, continuously capturing the structure and change process of the spatial scene of the earth’s surface, truly recording the fine scene information and motion target information, providing people with rich video information. People are usually interested in foreground targets(motion targets) in video surveillance, and foreground target extraction is a prerequisite for motion target tracking and event monitoring, which directly affects the accuracy of monitoring. This paper addresses the foreground target extraction problem of surveillance video, proposes a foreground target extraction method for surveillance video under different application scenarios, and verifies the feasibility of the method through experiments.